webEmbedding

Overview Schema Source Related Servers Discussions Admin

replay_har_requests

Replay request specifications against HAR, near-HAR, or webEmbedding network manifests to return deterministic response matches for reliable offline testing.

Instructions

Replay request specs against a standard HAR, near-HAR, or webEmbedding network manifest and return deterministic response matches.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "har_path": "<har_path>"
    },
    "name": "replay_har_requests"
  }
}

Input Schema

Name	Required	Description
`consume`	No	When true (default), each recorded response is used once, so repeated identical requests step through the recorded responses in order.
`har_path`	Yes	Path to a HAR file, near-HAR JSON, or webEmbedding network/manifest.json to replay from.
`requests`	No	Requests to match against the archive: objects with url and optional method, id, postData. Omit to only summarize the archive.
`output_path`	No	Optional path to write the replay report JSON.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.3.13Nov 9, 2026

addedInput schema / properties / consume / description

Added value: +"When true (default), each recorded response is used once, so repeated identical requests step through the recorded responses in order."

addedInput schema / properties / har_path / description

Added value: +"Path to a HAR file, near-HAR JSON, or webEmbedding network/manifest.json to replay from."

addedInput schema / properties / output_path / description

Added value: +"Optional path to write the replay report JSON."

addedInput schema / properties / requests / description

Added value: +"Requests to match against the archive: objects with url and optional method, id, postData. Omit to only summarize the archive."

First observedv0.3.12Nov 2, 2026

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already state this is not read-only, not idempotent, and not destructive, so the safety profile is covered. The description adds the useful claim that response matches are deterministic, but it does not disclose that output_path writes a report file, which is the side effect behind readOnlyHint=false. With annotations doing the heavy lifting, this is an adequate rather than rich disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single front-loaded sentence with no filler and no repetition of the tool name. Nothing is wasted, though there is no structure signalling the summarize-only mode or the write-out behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter tool with no output schema, the description covers the core action but leaves out two behaviors an agent needs: omitting requests only summarizes the archive, and output_path writes a report file. Matching semantics, such as how method and postData affect matching, are also unexplained. It is minimally viable rather than complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and every parameter including consume, har_path, requests, and output_path is documented in the schema itself. The description adds no syntax, matching rule, or format detail beyond what the schema already provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Replay request specs against a standard HAR, near-HAR, or webEmbedding network manifest'. It names the accepted archive formats, which tells an agent precisely what input universe it handles. It does not differentiate itself from siblings such as capture_reference_bundle or verify_fidelity_report, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the tool for replaying recorded traffic, but the description never states when to use it instead of the capture, clone, or verify siblings. It also omits that leaving requests out turns the call into an archive summary, which is a real usage mode documented only in the schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.